Scaling Monosemanticity person
3 mentions · across 1 show
https://transformer-circuits.pub/2024/scaling-monosemanticity
Relationship map
podcastsolid = outgoing · dashed = incoming
Connections 4
mentioned 2
-
0.45
evidence rules-v4
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
-
0.45
evidence rules-v4
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity
references 2
-
0.38
evidence rules-v4
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
-
0.38
evidence rules-v4
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity
Heard in
- Machine Learning Street Talk (MLST)2 episodes
Mentioned in episodes
-
2024-08-22 · Machine Learning Street Talk (MLST) · via mentioned · 0.45
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
-
2024-08-22 · Machine Learning Street Talk (MLST) · via references · 0.38
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
-
2024-07-18 · Machine Learning Street Talk (MLST) · via mentioned · 0.45
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity
-
2024-07-18 · Machine Learning Street Talk (MLST) · via references · 0.38
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity
All extracted evidence for this entity (4)
description:link Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
description:link Sara Hooker - Why US AI Act Compute Thresholds Are Misguided
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity
description:link Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
Link in episode "Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)": https://transformer-circuits.pub/2024/scaling-monosemanticity
description:link Sara Hooker - Why US AI Act Compute Thresholds Are Misguided
Link in episode "Sara Hooker - Why US AI Act Compute Thresholds Are Misguided": https://transformer-circuits.pub/2024/scaling-monosemanticity